Data-Driven Face Mask Detection and Alert System Utilizing Haar Cascade Classifier

Abstract

The COVID-19 pandemic has brought to light the pivotal role of face masks in curbing the transmission of contagious illnesses. As societies strive to uphold mask mandates in public areas, there has been a surge of interest in automated face mask detection systems. This study presents a novel data-centric methodology for crafting a reliable face mask detection and notification system leveraging the Haar cascade classifier. Our approach hinges on a meticulously curated dataset comprising images of individuals both with and without masks. Through the adept utilization of feature extraction techniques and machine learning algorithms, our system learns to discern masked faces from their unmasked counterparts in real-time scenarios. The experimental outcomes of our study attest to the efficacy of our proposed system, showcasing commendable accuracy in detecting face masks. This substantiates its viability for deployment across diverse public settings, bolstering the arsenal of public health safety measures. The seamless integration of our system stands poised to fortify efforts aimed at safeguarding community well-being amidst the persistent threat of infectious diseases. Key words: Data, Mask , Deep Learning, Hybrid.